Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    benchmark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    มต
    -0.07
     リ
    -0.07
     ResourceManager
    -0.07
     fus
    -0.07
    UU
    -0.07
    -0.07
    产
    -0.07
     apples
    -0.07
     secretion
    -0.07
     міської
    -0.06
    POSITIVE LOGITS
     benchmark
    0.07
    .work
    0.07
     criterion
    0.07
     веч
    0.06
     hlavně
    0.06
     Benchmark
    0.06
     kiện
    0.06
     Beacon
    0.06
     Summit
    0.06
     undo
    0.06
    Act Density 0.007%

    No Known Activations